基于SwinTransformer和归一化流的色织物表面缺陷检测

打开文本图片集

中图分类号：TS101.9 文献标志码：A DOI：10.13338/j.issn.1006-8341.2025.03.005

Defect detection of yarn-dyed fabric based on Swin Transformer and normalizing flow

ZHANG Hongwei，ZHANG Siyi，WANG Haibo （School of Electronics and Information，Xi'an Polytechnic University，Xi'an 7loo48，China）

Abstract Traditional deep learning methods are limited by the scarcity of defect samples，complex background and difficult identification of smalltarget defects in fabric defect detection.In response to the problems，an unsupervised fabric defect detection and location method based on Swin Transformer and normalized flow was proposed. First，in the training stage，only defect-free fabric images were used to construct the training set，and Swin Transformer was used to extract multi-scale features. Then，a probability density estimation model was established using the normalized flow to model the distribution of normal sample features，so that the model can learn the potential spatial representation of normal fabric features. In the inference stage，the features of the fabric image to be measured were projected onto the learned feature distribution and their anomaly scores were calculated. Finally，the defect area of fabric was detected and located by anomaly fraction diagram. The experimental results show that this method can effctively learn the feature distribution of normal fabrics and accurately detect and locate various fabric defects under complex background. On the YDFI-1 data set，the proposed method achieves 98.4% image-level AUROC and 96.9% pixellevel AUROC，which is significantly better than the existing unsupervised fabric defect detection methods.This method does not need defect samples and defect labeling，and only relies on the feature distribution of normal samples for defect identification，thus improving the generalization ability and robustness of detection.

Keywordsfabric defect detection； yarn-dyed fabric; Swin Transformer;unsupervised defect detection；probability density estimation modeling；normalizing flow

0 引言

如今，色织物以其丰富多彩的色泽和多样的纹理风格，广泛应用于人们的日常生活，满足了消费者对个性化、多样化纺织品的需求。（剩余13448字）